arize-phoenix-evals: v2.12.0
2.12.0 (2026-03-24) Features evals: accept structured data eval inputs (5f33727) Bug Fixes evals: allow prompt_template and kwargs in built-in classification evaluators (2ec192c) Pin LiteLLM <1.82.7 to mitigate supply chain attack (48970b6) playground: prevent OTel context leak causing duplicate trace_id in dataset runs (2a24625) Documentation evals...